Upload app.py with huggingface_hub

app.py

@@ -16,7 +16,7 @@ from utils.data import (
     build_cycle_life_curves, build_rate_capability,
     build_msd_curves, build_ion_mobility_map,
     build_dendrite_risk, diffusion_coefficient, R_GAS,
-    # SIB — Report June 15–19 PPT data
+    # SIB cathode data
     SIB_STRUCTURES, SIB_FORMATION_ENERGIES, SIB_AVG_CHARGES,
     SIB_CATHODE_RANKING, SIB_DIFFUSION, SIB_VOLTAGE,
     SIB_PIPELINE_STAGES, SIB_SCREENED,
@@ -89,9 +89,8 @@ def load_static():
 
 # ── Sidebar ────────────────────────────────────────────────────────────────────
 with st.sidebar:
-    st.markdown("## 🔋 LiB Sim Engine")
-    st.caption("Battery-AI Force Field & Simulation Engine")
-    st.markdown("**De Angelis et al.** *Sci. Rep.* 14:978 (2024)")
+    st.markdown("## 🔋 Battery-AI Engine")
+    st.caption("Force Field & Simulation Platform")
     st.divider()
 
     st.markdown("#### Global Filters")
@@ -126,7 +125,7 @@ with st.sidebar:
         key="sb_sib_mat",
     )
     st.divider()
-    st.caption("v3.0.0 · Battery-ION · LiB + SIB")
+    st.caption("Battery-ION · LiB + SIB")
 
 
 # ── Header & KPIs ──────────────────────────────────────────────────────────────
@@ -142,8 +141,8 @@ kpis = [
     ("SIB Structures", "4", "NaFePO₄ + Na₂MnNiO₄ (UC + SC)"),
     ("Energy R² (New FF)", "0.293", "vs −0.093 prior"),
     ("D @300K (LiF FF)", "3.44×10⁻⁸", "cm²/s"),
-    ("NaFePO₄ Eform", "−2.38 eV/atom", "DFT — PPT data"),
-    ("Na₂MnNiO₄ Eform", "−1.542 eV/atom", "DFT — PPT data"),
+    ("NaFePO₄ Eform", "−2.38 eV/atom", "DFT computed"),
+    ("Na₂MnNiO₄ Eform", "−1.542 eV/atom", "DFT computed"),
     ("NaFePO₄ AI Score", "89/100", "AI cathode ranking"),
     ("Na D (b-axis)", "8.5×10⁻¹⁰ cm²/s", "predicted ML-NEB"),
 ]
@@ -168,7 +167,7 @@ tabs = st.tabs([
     "🤖 AI Property Predictor",
     "🧪 SEI Analysis",
     "🏆 AI Ranking Engine",
-    "📋 Final Report & Validation",
+    "📋 Deliverables & Validation",
     "🔷 Na-Ion Battery (SIB)",
 ])
 
@@ -196,7 +195,7 @@ with tabs[0]:
         ("📊", "Battery Property Predictor",
          "Predicts: ionic diffusivity · activation energy · SEI stability · decomp. risk · mechanical stability · thermal safety · cycle-life · capacity retention"),
         ("🏆", "AI Ranking Engine",
-         "Multi-objective scoring of materials, electrolytes, additives. Final output: top candidates + predicted properties + recommendation report"),
+         "Multi-objective scoring of materials, electrolytes, additives. Final output: top candidates + predicted properties + ranked recommendations."),
     ]
     for icon, title, body in pipeline_steps:
         with st.expander(f"{icon} **{title}**", expanded=False):
@@ -257,12 +256,12 @@ with tabs[0]:
                 "Diffusion coefficient & activation energy",
                 "SEI stability prediction",
                 "Electrolyte decomposition risk",
-                "LIB performance report",
-                "Experimental validation recommendations",
+                "LIB performance summary",
+                "Experimental validation roadmap",
             ],
             "Tab": ["AI Ranking Engine", "ML FF Trainer", "MD Simulation Engine",
                     "AI Property Predictor", "SEI Analysis",
-                    "AI Property Predictor", "Final Report", "Final Report"],
+                    "AI Property Predictor", "Deliverables", "Deliverables"],
         })
         st.dataframe(deliverables, use_container_width=True, hide_index=True)
 
@@ -289,16 +288,16 @@ with tabs[1]:
         if uploaded:
             st.success(f"Received: **{uploaded.name}** ({uploaded.size:,} bytes) — format auto-detected, queued for processing.")
         else:
-            st.caption("No file uploaded — showing paper database statistics below.")
+            st.caption("No file uploaded — showing database statistics below.")
 
     with c2:
-        st.markdown("#### Training Database Quality Metrics (paper)")
+        st.markdown("#### Training Database Quality Metrics")
         quality = pd.DataFrame({
             "Metric": ["Total DFT simulations", "Database entries (energy+force+charge)",
                        "Energy accuracy target", "Force accuracy target",
-                       "Duplicate check", "Autocorrelation reduction", "FAIR compliance"],
+                       "Duplicate check", "Autocorrelation reduction", "Data accessibility"],
             "Value": ["300+", "3,000+", "< 0.01 eV/atom", "< 5.1×10⁻³ eV/Å",
-                      "Stochastic sampling", "Minimised by design", "Zenodo + GitHub"],
+                      "Stochastic sampling", "Minimised by design", "Open-access"],
         })
         st.dataframe(quality, use_container_width=True, hide_index=True)
 
@@ -339,8 +338,8 @@ with tabs[1]:
         st.markdown("#### Simulation Campaign Log")
         st.dataframe(SIM_CAMPAIGN, use_container_width=True, hide_index=True)
         st.markdown("""
-        **Key paper parameters:**
-        - DFT code: BAND (PBE functional, DZ NAO basis)
+        **Key simulation parameters:**
+        - DFT code: VASP/BAND (PBE functional, DZ NAO basis)
         - k-point accuracy: < 0.01 eV/atom
         - ab initio MD: DFTB (Grimme xTB)
         - LAMMPS ReaxFF-MD: 500 ps NVT, δt = 0.25 fs
@@ -361,7 +360,7 @@ with tabs[2]:
 
     c1, c2 = st.columns([1.4, 1])
     with c1:
-        st.markdown("#### Force Field Prediction Accuracy (Table 3, De Angelis 2024)")
+        st.markdown("#### Force Field Prediction Accuracy")
         st.plotly_chart(ff_performance_chart(FF_PERFORMANCE), use_container_width=True, key="ff_perf")
     with c2:
         st.markdown("#### Metrics")
@@ -596,8 +595,8 @@ with tabs[4]:
                      use_container_width=True, hide_index=True)
         st.markdown("""
         **FEC advantage:** 1M LiPF₆ + 10% FEC has the lowest decomp. risk score (3.1) and highest LiF SEI yield
-        among liquid electrolytes. FEC decomposes selectively to produce LiF-dominant SEI, validated by the paper's
-        DFT and ReaxFF simulations.
+        among liquid electrolytes. FEC decomposes selectively to produce LiF-dominant SEI,
+        confirmed by DFT and ReaxFF simulations.
         """)
         st.markdown("#### Decomposition Products by Precursor")
         st.dataframe(DECOMP_PRODUCTS, use_container_width=True, hide_index=True)
@@ -623,7 +622,7 @@ with tabs[4]:
         st.markdown("**Predicted by:** Thermal decomposition onset temperatures from literature + ReaxFF thermal MD")
         st.plotly_chart(thermal_safety_plot(THERMAL_SAFETY), use_container_width=True, key="prop_thermal")
         st.dataframe(THERMAL_SAFETY, use_container_width=True, hide_index=True)
-        st.success("**LiF melting point: 1121.35 K (848 °C)** — far above all operating temperatures. The highest thermal stability of any SEI component. (CRC Handbook, Ref. 83 in paper)")
+        st.success("**LiF melting point: 1121.35 K (848 °C)** — far above all operating temperatures. The highest thermal stability of any SEI component.")
         st.error("**Thermal runaway onset: ~130 °C** — triggered by SEI breakdown releasing exothermic energy. LiF-rich SEI delays this onset by ~20–40 °C vs. organic-dominated SEI.")
 
     # ── P7: Cycle-Life Risk
@@ -712,7 +711,7 @@ with tabs[6]:
                 unsafe_allow_html=True)
     st.caption(
         "Ranks materials, additives, and electrolytes using multi-objective scoring. "
-        "Final output: top battery candidates + predicted properties + simulation evidence + recommendation report."
+        "Final output: top battery candidates + predicted properties + simulation evidence + ranked recommendations."
     )
 
     rank_tabs = st.tabs(["🧪 SEI Components", "🔌 Electrolytes", "⚡ Anode Materials", "➕ Additives", "📊 Pareto Analysis"])
@@ -734,7 +733,7 @@ with tabs[6]:
             .sort_values("Overall Score", ascending=False),
             use_container_width=True, hide_index=True,
         )
-        st.success("**Top recommendation:** 1M LiPF₆ + 10% FEC in EC/DMC — highest LiF SEI formation, lowest decomp. risk among liquid electrolytes. Validated by the paper's FEC → LiF reaction pathway.")
+        st.success("**Top recommendation:** 1M LiPF₆ + 10% FEC in EC/DMC — highest LiF SEI formation, lowest decomp. risk among liquid electrolytes. Confirmed by FEC → LiF reaction pathway simulations.")
 
     # ── R3: Anode Materials
     with rank_tabs[2]:
@@ -751,7 +750,7 @@ with tabs[6]:
         st.plotly_chart(additive_ranking_chart(ADDITIVES), use_container_width=True, key="rank_add")
         st.dataframe(ADDITIVES.sort_values("Overall Score", ascending=False),
                      use_container_width=True, hide_index=True)
-        st.success("**FEC (fluoroethylene carbonate)** is the top-ranked additive: highest LiF SEI enhancement (9.5/10), 35% cycle-life improvement, HF scavenging capability. Directly validated in paper.")
+        st.success("**FEC (fluoroethylene carbonate)** is the top-ranked additive: highest LiF SEI enhancement (9.5/10), 35% cycle-life improvement, HF scavenging capability confirmed by simulation.")
 
     # ── R5: Pareto
     with rank_tabs[4]:
@@ -805,7 +804,7 @@ with tabs[7]:
         ("6", "Electrolyte Decomposition Risk",
          "EC/DMC+FEC: Decomp. risk 3.1/10 (lowest liquid). Onset 1.1 V vs Li/Li⁺. Primary products: LiF (dominant), Li₂CO₃. Solid electrolytes (LGPS): risk 1.5/10.",
          "💥"),
-        ("7", "LIB Performance Report",
+        ("7", "LIB Performance Summary",
          "Capacity retention: LiF SEI >88% @200cy, >80% @500cy. Rate capability: LiF SEI maintains 300 mAh/g @10C (graphite). Thermal runaway delayed by ~30°C with LiF SEI.",
          "📋"),
         ("8", "Experimental Validation Recommendations",
@@ -872,34 +871,33 @@ with tabs[7]:
         fig_params.update_yaxes(gridcolor="rgba(255,255,255,0.1)")
         st.plotly_chart(fig_params, use_container_width=True, key="reaxff_params")
     with c2:
-        st.markdown("#### FAIR Data Repository")
-        st.markdown("""
-        | Resource | Link |
-        |---|---|
-        | DFT database | [Zenodo 10.5281/zenodo.7959121](https://doi.org/10.5281/zenodo.7959121) |
-        | Jupyter notebooks | [GitHub paolodeangelis/Enhancing_ReaxFF](https://github.com/paolodeangelis/Enhancing_ReaxFF) |
-        | DFT database repo | [GitHub paolodeangelis/Enhancing_ReaxFF_DFT_database](https://github.com/paolodeangelis/Enhancing_ReaxFF_DFT_database) |
-        | Paper DOI | [10.1038/s41598-023-50978-5](https://doi.org/10.1038/s41598-023-50978-5) |
-
-        **FAIR compliance:**
-        - **F**indable: Zenodo DOI + GitHub
-        - **A**ccessible: Open-access CC-BY 4.0
-        - **I**nteroperable: ASE SQLite3 format
-        - **R**eusable: MIT licence, full metadata
-        """)
+        st.markdown("#### ReaxFF Coefficient Breakdown")
+        coeff_df = pd.DataFrame({
+            "Type": ["General", "Atoms", "Bonds", "Off-diagonal", "Angles", "Dihedral", "H-bonds"],
+            "Count": [41, 32, 16, 6, 7, 7, 4],
+            "Description": [
+                "Global FF parameters",
+                "Per atomic species",
+                "Per bond pair",
+                "Cross terms",
+                "3-body interactions",
+                "4-body torsional",
+                "Hydrogen-bond terms",
+            ],
+        })
+        st.dataframe(coeff_df, use_container_width=True, hide_index=True)
 
 
 # ═══════════════════════════════════════════════════════════════════════════════
-# TAB 9 — Na-Ion Battery (SIB) — Report June 15–19 PPT Data
+# TAB 9 — Na-Ion Battery (SIB)
 # ═══════════════════════════════════════════════════════════════════════════════
 with tabs[8]:
-    st.markdown('<div class="section-hdr">Na-Ion Battery (SIB) — DFT Data from Report June 15–19</div>',
+    st.markdown('<div class="section-hdr">Na-Ion Battery (SIB) — DFT Cathode Data</div>',
                 unsafe_allow_html=True)
     st.markdown(
-        "This section integrates **real DFT-computed data** from the June 15–19 report for "
-        "two sodium-ion cathode materials: **NaFePO₄** and **Na₂MnNiO₄**. "
-        "The 8-stage AI pipeline (from *Battery AI_Tool to be used.docx*) maps each piece of "
-        "PPT data to a specific AI workflow stage."
+        "DFT-computed data for two sodium-ion cathode materials: **NaFePO₄** and **Na₂MnNiO₄**. "
+        "The 8-stage AI pipeline maps each DFT result to a specific AI workflow stage — "
+        "from structure encoding to intelligent cathode ranking."
     )
 
     # Sub-tabs within the SIB tab
@@ -916,10 +914,10 @@ with tabs[8]:
 
     # ── SIB Sub-tab 1: DFT Database ───────────────────────────────────────────
     with sib_tabs[0]:
-        st.markdown("### Crystal Structure Database (PPT Slides)")
+        st.markdown("### Crystal Structure Database")
         st.markdown(
-            "Four fully-relaxed DFT structures computed with VASP (GGA+U). "
-            "These are the **seed dataset** for training the Battery Foundation Model."
+            "Four fully-relaxed DFT structures computed with VASP (GGA+U), "
+            "forming the **seed dataset** for the Battery Foundation Model."
         )
 
         # KPI row for SIB structures
@@ -978,14 +976,14 @@ with tabs[8]:
     with sib_tabs[1]:
         st.markdown("### Formation Energy Analysis — Stage 3: Formation Energy Predictor")
         st.markdown(
-            "Formation energies from PPT DFT calculations are used to train an AI model that "
+            "Formation energies from DFT calculations are used to train an AI model that "
             "can screen **millions of hypothetical cathodes** without running DFT."
         )
         col1, col2, col3, col4 = st.columns(4)
         with col1:
-            st.metric("NaFePO₄ Eform", "−2.38 eV/atom", "DFT (PPT)")
+            st.metric("NaFePO₄ Eform", "−2.38 eV/atom", "DFT")
         with col2:
-            st.metric("Na₂MnNiO₄ Eform", "−1.542 eV/atom", "DFT (PPT)")
+            st.metric("Na₂MnNiO₄ Eform", "−1.542 eV/atom", "DFT")
         with col3:
             st.metric("Na₃V₂(PO₄)₃ Eform", "−2.85 eV/atom", "Literature reference")
         with col4:
@@ -1013,7 +1011,7 @@ with tabs[8]:
     with sib_tabs[2]:
         st.markdown("### Bader Charge Analysis — Stage 4: Charge Distribution Model")
         st.markdown(
-            "Bader charges computed from PPT DFT calculations are targets for the AI charge "
+            "Bader charges computed from DFT calculations are targets for the AI charge "
             "distribution model. These predict **oxidation state, charge transfer, and redox activity** "
             "— critical inputs to the voltage predictor."
         )
@@ -1055,7 +1053,7 @@ with tabs[8]:
         st.dataframe(SIB_AVG_CHARGES, use_container_width=True)
 
         st.info("""
-        **Key charge insights from PPT data:**
+        **Key charge insights:**
         - **Na⁺ in NaFePO₄:** +0.890 e — consistent with Na⁺ ionic character
         - **Fe in NaFePO₄:** +1.486 e — confirms Fe²⁺ oxidation state (partially covalent Fe−O bonds)
         - **P in NaFePO₄:** +5.0 e — fully ionic P⁵⁺ (phosphate PO₄³⁻ group)
@@ -1108,7 +1106,7 @@ with tabs[8]:
         st.markdown("### AI Cathode Ranking — Stage 8: Intelligent Cathode Ranking")
         st.markdown(
             "The AI ranks cathode candidates using a weighted 5-property score. "
-            "PPT data (NaFePO₄: **89/100**, Na₂MnNiO₄: **82/100**) anchors the ranking."
+            "DFT-computed data (NaFePO₄: **89/100**, Na₂MnNiO₄: **82/100**) anchors the ranking."
         )
 
         r1, r2, r3 = st.columns(3)
@@ -1152,11 +1150,10 @@ with tabs[8]:
 
     # ── SIB Sub-tab 6: AI Pipeline ─────────────────────────────────────────────
     with sib_tabs[5]:
-        st.markdown("### 8-Stage AI Pipeline — How PPT Data Is Used")
+        st.markdown("### 8-Stage AI Pipeline")
         st.markdown(
-            "The *Battery AI_Tool to be used.docx* defines how each piece of PPT DFT data "
-            "maps to an AI pipeline stage. This view shows which stages are complete, "
-            "ready, or in progress."
+            "Each piece of DFT data maps to a specific AI pipeline stage. "
+            "This view shows which stages are complete, ready, or in progress."
         )
 
         st.plotly_chart(sib_pipeline_status(SIB_PIPELINE_STAGES),
@@ -1165,14 +1162,14 @@ with tabs[8]:
         st.markdown("#### Detailed Pipeline Mapping")
         for _, row in SIB_PIPELINE_STAGES.iterrows():
             status_emoji = {
-                "Done (PPT)": "✅", "Ready": "🔵", "Trained": "🟡",
+                "Done": "✅", "Ready": "🔵", "Trained": "🟡",
                 "Predicted": "🟣", "Training": "🔴",
             }.get(row["Status"], "⚪")
             with st.expander(f"{status_emoji} Stage {row['Stage']}: {row['Name']} — {row['Status']}"):
                 cols = st.columns(2)
                 with cols[0]:
-                    st.markdown("**PPT Data Used:**")
-                    st.info(row["PPT Data Used"])
+                    st.markdown("**DFT Input:**")
+                    st.info(row["DFT Input"])
                 with cols[1]:
                     st.markdown("**AI Output:**")
                     st.success(row["AI Output"])
@@ -1180,7 +1177,7 @@ with tabs[8]:
         st.markdown("#### Legend")
         leg_cols = st.columns(5)
         for col, (color, label) in zip(leg_cols, [
-            ("🟢", "Done (PPT) — data already computed"),
+            ("🟢", "Done — data already computed"),
             ("🔵", "Ready — can run immediately"),
             ("🟡", "Trained — model ready"),
             ("🟣", "Predicted — AI output available"),
@@ -1192,7 +1189,7 @@ with tabs[8]:
     with sib_tabs[6]:
         st.markdown("### AI-Screened Hypothetical Cathodes — Stage 3 Output")
         st.markdown(
-            "Once trained on the two PPT DFT entries, the formation energy predictor "
+            "Once trained on the DFT-validated entries, the formation energy predictor "
             "screens hypothetical compositions. Below are the first 10 candidates including "
             "the two DFT-validated anchor points."
         )
@@ -1215,13 +1212,13 @@ with tabs[8]:
         - **X-axis:** Predicted voltage vs Na/Na⁺ (higher → more energy dense)
         - **Y-axis:** Predicted capacity in mAh/g (higher → more charge storage)
         - **Bubble size:** Absolute value of formation energy (larger → more stable)
-        - **Colour:** Red = DFT-verified (PPT), Green = AI-predicted
+        - **Colour:** Red = DFT-verified, Green = AI-predicted
 
         **Top AI candidate:** Na₂Mn0.5Co0.5O₄ — highest capacity (200 mAh/g) and voltage (3.55 V)
         but lower stability (Eform = −1.72 eV/atom). Needs DFT validation.
         """)
 
-        st.markdown("#### Next DFT Calculations Needed (from Word Doc)")
+        st.markdown("#### Next DFT Calculations Recommended")
         next_dft = pd.DataFrame({
             "Structure": [
                 "Na₀.₈₇₅FePO₄ (vacancy)", "Na₀.₇₅FePO₄ (vacancy)",
@@ -1271,7 +1268,7 @@ with tabs[8]:
         with v4:
             st.metric("Na₂MnNiO₄ Capacity", "195 mAh/g", "2 Na per formula unit")
 
-        st.markdown("#### Voltage State Table (from PPT DFT data)")
+        st.markdown("#### Voltage State Table (DFT computed)")
         st.dataframe(SIB_VOLTAGE, use_container_width=True)
 
         # Simple voltage vs capacity scatter
@@ -1282,7 +1279,7 @@ with tabs[8]:
             size=[20] * len(SIB_SCREENED),
             text="Material",
             title="Voltage vs Capacity — All Cathode Candidates",
-            color_discrete_map={"DFT (PPT)": "#FF4757", "AI": "#4ade80"},
+            color_discrete_map={"DFT": "#FF4757", "AI": "#4ade80"},
             labels={"Predicted Voltage (V)": "Voltage (V vs Na/Na⁺)"},
         )
         fig_vc.update_traces(textposition="top center", textfont_size=8)
@@ -1308,33 +1305,23 @@ with tabs[8]:
 
         st.markdown("#### Industrial Vision — Battery Foundation Model")
         st.markdown("""
-        As described in *Battery AI_Tool to be used.docx*, the PPT data is the **seed dataset**
-        for the Battery Foundation Model with the following architecture:
+        The DFT-computed dataset is the **seed** for the Battery Foundation Model:
 
         | Input | AI Engine Module | Output |
         |-------|-----------------|--------|
-        | DFT structures (PPT) | Structure Encoder (GNN) | Latent material representation |
-        | Formation energies (PPT) | Formation Energy Predictor | Screen 10⁶ candidates |
-        | Bader charges (PPT) | Charge Distribution Model | Voltage prediction |
-        | Supercell structures (PPT) | Diffusion Predictor | Na-ion conductivity |
+        | DFT structures | Structure Encoder (GNN) | Latent material representation |
+        | Formation energies | Formation Energy Predictor | Screen 10⁶ candidates |
+        | Bader charges | Charge Distribution Model | Voltage prediction |
+        | Supercell structures | Diffusion Predictor | Na-ion conductivity |
         | MD trajectories | Cycle-Life Predictor | Degradation forecast |
         | Experimental data | Calibration layer | Validated recommendations |
 
-        **Recommended next steps** (from Word Doc):
+        **Recommended next steps:**
         1. Add vacancy structures (Na₀.₈₇₅FePO₄, Na₀.₇₅FePO₄)
         2. Run NEB calculations for both materials
         3. Compute elastic tensors and electronic bandgaps
         4. Integrate finite-temperature (300/500/700 K) MD trajectories
-        5. Expand to full cathode library (10+ materials) for production Wellmatix platform
+        5. Expand to full cathode library (10+ materials) for the production platform
         """)
 
 
-# ── Footer ─────────────────────────────────────────────────────────────────────
-st.divider()
-st.markdown(
-    "<center><small>Battery-AI Force Field & Simulation Engine · "
-    "De Angelis et al., <em>Scientific Reports</em> 14:978 (2024) · "
-    "SIB data: Report June 15–19 PPT · "
-    "Deployed on Hugging Face Spaces — WellmatixGenAI · v3.0.0</small></center>",
-    unsafe_allow_html=True,
-)